Version 0.5.0

What's Changed

• feat: add model token usage stats to trace by @starpit in #762
• feat: add support for CodeBlocks with argv by @starpit in #756
• feat: add Usage tab to detail drawer for model blocks by @starpit in #778
• Systematically used localized expressions in the trace and add pdl__result in them by @mandel in #760
• feat: add Result tab to detail drawer by @starpit in #782
• doc: update readme ui screenshot to show usage metrics by @starpit in #793
• Copy the schema on the website by @mandel in #797

Full Changelog: v0.4.2...v0.5.0

Version 0.4.2

What's Changed

• feat: in UI allow pty execution to be canceled by @starpit in #673
• feat: switch ui tile run menu to split action dropdown by @starpit in #675
• default parameters for ollama_chat models by @vazirim in #689
• Change examples to ollama_chat by @jgchn in #691
• Grade School Math example by @esnible in #694
• Docstrings and examples for PDL concepts by @esnible in #693
• feat: ui temperature stability by @starpit in #697
• feat: add Pagination to UI by @starpit in #704
• demo hallucination trace by @vazirim in #705
• Structured decoding bug fix for watsonx, ollama + traceback for python code blocks by @vazirim in #708
• feat: interpreter should report (stderr) call start/end and timing by @starpit in #711
• feat: update interpreter to print out model response messages in async mode by @starpit in #717
• Update parse_str interface by @mandel in #741
• Support dev version of granite-io by @mandel in #742
• feat: pull models in rust by @starpit in #743
• feat: update auto-pull logic to run in parallel with pip install by @starpit in #744
• feat: use shasum as cache key for venv by @starpit in #748
• feat: add gsm8k demo to ui (demo9) by @starpit in #753
• Contributed values are expressions by @mandel in #754
• Use ${ pdl_context } as default value for the input field of a model block by @mandel in #757
• added litellm param to ignore structure decoding param in tools example by @vazirim in #750
• gsm8k with planning by @vazirim in #761

Full Changelog: v0.4.1...v0.4.2

Version 0.4.1

What's Changed

• Update granite-io dependency by @mandel in #641

Full Changelog: v0.4.0...v0.4.1

Version 0.4.0

What's Changed

• gsm8k examples and results by @vazirim in #322
• feat: in react ui Context tab, use breadcrumb ui to link to def site by @starpit in #380
• Add json-repair by @claudiosv in #279
• feat: in react ui, add Masonry view to replace Transcript view by @starpit in #395
• Asynchronous LLMs calls by @mandel in #284
• feat: in react UI, add Run button to support re-running program by @starpit in #431
• Add a max_iterations field to the repeat/until loop (and make until optional) and remove repeat/num_iterations loops. by @mandel in #434
• Granite 3.1 chat template fix by @vazirim in #433
• feat: add homebrew formula by @starpit in #447
• Unify repeat and for loops and add while by @mandel in #444
• feat: in react ui re-enable Replay/Run button and functionality by @starpit in #451
• intrinsics hallucination example by @vazirim in #464
• doc: update react ui build for production documentation by @starpit in #476
• feat: syntax highlight code in markdown blocks by @starpit in #480
• feat: in react ui, use pty for Run by @starpit in #492
• feat: add final result 'output of program' to react ui masonry by @starpit in #497
• removed old viewer by @vazirim in #510
• feat: add Platform field to model detail Summary tab by @starpit in #516
• modules implementation by @vazirim in #507
• New RAG example by @esnible in #427
• feat: initial support for showing structured model responses in detail ui by @starpit in #527
• updated PDL quick reference by @hirzel in #545
• feat: add opengraph meta info to ui by @starpit in #549
• Migrate some examples from Replicate to Ollama by @jgchn in #522
• Added Granite 3.2 chat template, template that works with ollama by @vazirim in #557
• model blocks can use the granite-io platform by @mandel in #529
• Join loop iterations as objects by @mandel in #580
• Add flexibility on the case of the values for the fields lang, parser, and mode by @mandel in #612
• Incorrect endpoint in Telemetry doc by @esnible in #619
• Deploy Ollama to run examples by @jgchn in #629

New Contributors

• @jgchn made their first contribution in #521

Full Changelog: v0.3.0...v0.4.0

Version 0.3.0

What's Changed

• Port pdl-live to react+patternfly+vite by @starpit in #253
• Embed PDL interpreter into react (tauri) app builds by @starpit in #350
• Remove BAM support by @mandel in #265
• Config options for model default parameters by @esnible in #266
• Add a match block by @mandel in #252
• Don't crash without log on keyboard exit by @esnible in #346
• lowered lower bound of litellm to 1.57.3 by @vazirim in #365

New Contributors

• @starpit made their first contribution in #253

Full Changelog: v0.2.0...v0.3.0

Version 0.2.0

Warning: This release introduce a non-backward compatible change: call blocks take closures as argument instead of function names. In practice, a function call like call: f must be replace by call: ${f}.

What's Changed

• The argument of call: is a closure, not a name by @mandel in #242
• Initial OpenTelemetry support by @esnible in #254
• Removed upper bound on LiteLLM version by @vazirim in #255
• Add comments to examples to make them more obvious by @esnible in #259

Full Changelog: v0.1.1...v0.2.0

Version 0.1.1

What's Changed

• remove None valued parameters when calling LLMs by @vazirim in #212
• Flush the output after each print in streaming mode by @mandel in #213
• support for expressions in function call args by @vazirim in #221
• Show the model name, and request info if possible, on error by @esnible in #226

New Contributors

• @trsudarshan made their first contribution in #209
• @esnible made their first contribution in #222

Full Changelog: v0.1.0...v0.1.1

Version 0.1.0

Warning: This release introduce a non-backward compatible change: implicit lastOf (lists of blocks) are not allowed anymore.

What's Changed

• Add support of Jinja code blocks by @mandel in #183
• Add support of PDL code blocks by @mandel in #185
• Enable richer data in messages to support function calling by @vazirim in #184
• Add localized expressions in AST by @mandel in #130
• Remove implicit lastOf by @mandel in #167
• changes to default parameters, structured decoding support by @vazirim in #205
• updated tools and react examples to use granite tool calling by @vazirim in #206

Full Changelog: v0.0.9...v0.1.0

Version 0.0.9

What's Changed

• Obtaining raw output from model calls by @vazirim in #165
• Fix implicit unused analysis by @mandel in #158
• support for structured decoding, removed default watsonx parameters by @vazirim in #168
• Remove useless computation during model calls using liteLLM by @mandel in #171
• Support for Python 3.13 by @mandel in #166
• doc: added ollama API env variable by @eloycoto in #175
• bug fix for LLM function calling by @vazirim in #178

New Contributors

• @eloycoto made their first contribution in #175

Full Changelog: v0.0.8...v0.0.9

v0.0.8

What's Changed

• Tutorial updates by @vazirim in #152
• Emit a warning if a result is implicitly ignored by @mandel in #127
• Update documentation by @mandel in #155
• Use new granite models by @vazirim in #160